摘要
歧义是自然语言特别是汉语的显著特点和普遍现象,也是当前汉英机器翻译系统的主要处理难点之一。通过对其中一些常见汉语歧义结构的分析,提出一种基于实例的歧义结构消解方法。由于歧义结构的对应实例具有较高的“结构”上的代表性,通过与这些实例的相似性比较可以较准确地把握待消歧语段的内部结构。
Ambiguity is common in natural languages,especially in Chinese.It is also one of the most difficult points in Chinese-
English machine translation.Some ambiguity structures were analyzed,and then an example-based disambiguation method was
put forwad.Owing to the better representation of examples corresponding to some ambiguity structures,the inner structure of
disambiguating segment maght be gained more accurately by comparing the similarity with those examples.
出处
《计算机工程与设计》
CSCD
2004年第5期688-690,共3页
Computer Engineering and Design
基金
安徽省教育厅自然科学研究基金(2004KJ060)
